Skip to main content

gpt-oss-20b vs o1-mini

Specgpt-oss-20bo1-mini
Respan Index13.6 (#165)13.9 (#163)
Blended price per 1M$0.036$1.93
Context window131K-
Input / output per 1M$0.018 / $0.09$1.1 / $4.4
Max output131K-
Inputtexttext
Released2025-08-052024-09-12

Respan Index by category

Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.

Categorygpt-oss-20bo1-mini
Coding4.7 gpt-oss-20b3.8 o1-mini
Agents7.8* gpt-oss-20b8.2* o1-mini
Reasoning18.5 gpt-oss-20b18.5 o1-mini
Knowledge & language7.0* gpt-oss-20b7.3* o1-mini
Human preference34.5 gpt-oss-20b36.9 o1-mini

* Estimated: no published scores in that category. How the Respan Index works

Benchmarks both report

gpt-oss-20b leads on 3 of the 4 benchmarks both report. Higher is better. Each score links to where it was published.

Benchmarkgpt-oss-20bo1-mini
LMArena Elo13181337
GPQA Diamond71.5%62.4%
OTIS Mock AIME 2024-2025 (Epoch AI)65.3%46.9%
WeirdML (Håvard Tveit Ihle)40.9%36.3%

FAQ

Is gpt-oss-20b better than o1-mini?

o1-mini scores 13.9 on the Respan Index (#163), ahead of gpt-oss-20b at 13.6 (#165). gpt-oss-20b leads on 3 of the 4 benchmarks both report.

Which is cheaper, gpt-oss-20b or o1-mini?

gpt-oss-20b lists at $0.018 input and $0.09 output per 1M tokens; o1-mini at $1.1 and $4.4. gpt-oss-20b is 53x cheaper per token at list price.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.